International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 07 Issue: 08 | Aug 2020
p-ISSN: 2395-0072
www.irjet.net
Plant Disease Identification and Automatic Chemical Sprayer Ramanna Havinal1, GuruPrasad B N2, Manoj B L3, Ravikumar K S4 1Professor
Electronics and communication Engineering Dept, Maharaja Institute of Technology Musore, India Electronics and communication Engineering Dept, Maharaja Institute of Technology Musore, India ---------------------------------------------------------------------***---------------------------------------------------------------------2-4Student,
Abstract: Agriculture is the most important sector for survival of living organisms. There is need for development in agriculture to provide enough food this fast-growing population. The history of agriculture shows that techniques in agriculture improved gradually. There is a huge gap between technologies what we have and present agricultural techniques in India. The equipment what we are building in this project identifies the disease in plants when we take the picture of the diseased plant leaf through camera and later the pesticide is sprayed on crops based on diseased identified. Disease identification is done using image processing techniques with the help of Raspberry pi development board where the programming is done in Python language. Image Pre-processing is done with the help of TensorFlow library which is developed, released and maintained by Google. Plant Diseased leaf part is clustered using the K-means clustering technique which is best to our project. After K-means clustering to be more precise we are using SVM expanded as Support Vector Machine which is used to classify the disease in that particular leaf. After image classification and disease detection, proper pesticide which is stored in container can be sprayed to that plant through the nozzle. By this project plant diseases can be identified at the early stage and can be cured. So that the final yield can be more productive and also chemical free, since we spray only required amount of pesticides which is prescribed by the government.
will reduce the health issues related to farmers. The present work proposes an efficient method to detect the paddy leaf and tomato leaf diseases using image processing techniques. In this paper we have implemented the image processing techniques detect diseases on paddy and tomato leaf. Once the disease is detected spraying of pesticides is done
Key Words: Plant disease, Segmentation, Chemical Spray Leaf
Plant disease identification is a challenging task. Generally diseases are seen on the leaves or stems of the plant. Proposed approach is to detect the paddy and tomato leaf diseases using image processing techniques.. The objectives of proposed study are 1. Classification of leaf disease 2. Spraying appropriate pesticide. 3. Reduce time between identification and spraying of chemical.
1. INTRODUCTION Agriculture has played a key role in the development Decrease in agricultural production will affect the total economy. Therefore, Proper management of various resources such as soil, seed, water, fertilizers is required for sustainability. Detecting the disease plays a major role as diseases are inevitable. The pigmentation, fruit-sets and nutritive value of the fruits are affected by temperature and light intensity. Plant are very susceptible to diseases caused by fungi, bacteria, and viruses. Quantity and quality of the agricultural products are affected by plant diseases found on plants. Manual plant diseases identification is time consuming and does not give accurate results. Long exposure to pesticides will have health effect on farmers. Automatic spraying of pesticides Š 2020, IRJET
|
Impact Factor value: 7.529
|
Most of the plant diseases are triggered by fungi, bacteria, and viruses therefore detection of plant disease is essential. Morphological changes in leaves are the primary stage of Fungi. Bacteria are considered more embryonic than fungi. They have simpler life cycles and identified by morphological changes in leaves. Detection and classification of the natural plant disease is normally performed by bare eye observation and chemical test. In large scale farming it is impossible to observe each and every plant, every day. Farmers are unaware of non-native diseases. Consultation of experts for this might be time consuming and costlier. Unnecessary use of pesticides is dangerous and harmful to natural resources such as water, soil, air, food chain etc. Care has to be taken such that there should be less contamination of food products with pesticides. We need a technique to detect the plant diseases and spray the required amount of chemical to the plant. The proposed study aims for automatic plant disease identification and spray chemicals automatically
2. LITERATURE SURVEY Savita M Ghaiwat [1] developed a system to identify disease identification of chilli plant leaves. Sanjay B[2] proposed a model to automatically identify and classify the diseases in pomegranate fruit[2]. Study found Bacterial Blight, Cercosporin fruit spot, Fruit Rot, Alternaria fruit Spot diseases on pomegranate fruit. Mrinalini R[3] explains about the image processing steps[3] and Neural Network used in identification for fast and accurate recognition and classification of diseases. It ISO 9001:2008 Certified Journal
|
Page 3926